AI OS Blueprint

Framework: The OS Stack Scorecard
Worth $500/hr consultant time. Yours for $39.

---

What This Skill Does

Takes you from "I use Claude like a chatbot" to "Claude is my operating system." Covers persistent memory, skill architecture, context hooks, and sub-agent routing. Includes a full audit of your current setup with a scored gap analysis and rebuild plan.

Problem it solves: The jump from ChatGPT user to AI-native operator is a mindset shift, not just a tooling upgrade. Most people add one automation at a time and wonder why nothing compounds. This blueprint gives you the architecture that makes everything stack.

---

The OS Stack Scorecard

A diagnostic framework that audits your current AI setup across 5 layers and produces a prioritized rebuild plan. Score your stack, find the bottleneck, fix it first.

The 5 Layers of an AI OS

CODEBLOCK0

Fix Layer 1 before Layer 2. Fix Layer 2 before Layer 3. Etc.
Skipping layers is why most AI setups plateau.

---

OS Stack Scorecard: Full Audit

Layer 1 — Foundation Audit

Score each item 0-2:

Component	0 (Missing)	1 (Partial)	2 (Done)	Your Score
AI client installed (Claude Desktop / OpenClaw)	None	Old version	Current
MCP servers connected

0 tools | 1-2 tools | 3+ tools | |
| API keys stored securely | In chat history | In .env file | In secrets manager | _ |
| Config file backed up | Never | Occasionally | Version controlled | _ |
| Restart/reload procedure known | Unknown | Sometimes works | Documented | _ |

Layer 1 Score: _ / 10

If Layer 1 < 6: Stop. Fix foundation before anything else.
→ Install MCP Server Setup Kit (sold separately) to fix this layer.

---

Layer 2 — Context & Memory Audit

Score each item 0-2:

Component	0 (Missing)	1 (Partial)	2 (Done)	Your Score
Persistent memory file exists	None	Informal notes	Structured MEMORY.md
Agent knows your role/context

Starts fresh each session | Some in system prompt | Full context file | |
| Daily memory updated regularly | Never | Inconsistently | Every session | _ |
| Long-term decisions captured | Lost | In chat history | In searchable file | _ |
| Context files are version controlled | No | Sometimes | Yes, always | _ |

Layer 2 Score: _ / 10

If Layer 2 < 6: Agent has amnesia. Everything you teach it, it forgets.
→ See Memory Architecture section below.

---

Layer 3 — Skill Architecture Audit

Score each item 0-2:

Component	0 (Missing)	1 (Partial)	2 (Done)	Your Score
Skills installed for your use cases	Using base model only	1-3 skills	5+ targeted skills
Skills have named frameworks

Generic prompts | Some structure | Proprietary frameworks | |
| Skills are version controlled | No | Sometimes | Yes | _ |
| Skills are tested before use | Never | Ad hoc | Formal test per skill | _ |
| Skill catalog documented | No | Mental map only | Written index | _ |

Layer 3 Score: _ / 10

If Layer 3 < 6: You're reinventing the wheel every session.
→ See Skill Architecture section below.

---

Layer 4 — Agent Routing Audit

Score each item 0-2:

Component	0 (Missing)	1 (Partial)	2 (Done)	Your Score
You know when to use sub-agents	Never use	Occasionally	Systematically
Tasks are routed by type

One agent does everything | Some routing | Model × task matrix | |
| Expensive model use is justified | Always default | Sometimes cheap | Cheapest model that works | _ |
| Parallel work happens | Always sequential | Sometimes parallel | Default parallel | _ |
| Agent output is reviewed before action | Never | Sometimes | Always for risky ops | _ |

Layer 4 Score: _ / 10

If Layer 4 < 6: You're using a supercomputer like a calculator.
→ See Agent Routing section below.

---

Layer 5 — Outputs & Integrations Audit

Score each item 0-2:

Component	0 (Missing)	1 (Partial)	2 (Done)	Your Score
Agent outputs land in the right tools	Copy-paste manually	Partially automated	Fully integrated
Slack notifications configured

None | Manual | Automated via loop | |
| Notion/Linear/GitHub updated automatically | Never | Sometimes | Systematically | _ |
| Outputs are searchable/retrievable | Lost after session | In notes | In indexed system | _ |
| Feedback loops exist (agent learns from output) | None | Informal | Structured | _ |

Layer 5 Score: _ / 10

Total OS Stack Score: _ / 50

---

Scorecard Interpretation

Total Score	Status	Priority Action
45-50	AI-Native Operator	Optimize costs + scale loops
35-44

Advanced User | Fix weakest layer, add routing |
| 25-34 | Intermediate | Memory + skill architecture gaps |
| 15-24 | Beginner | Start with Layer 1-2 rebuild |
| 0-14 | Day 1 | Follow the full OS Build Order below |

---

The OS Build Order

Build exactly in this order. Do not skip.

Phase 1: Foundation (Week 1, ~4 hours)

Goal: Agent is connected to your tools and can receive commands.

CODEBLOCK1

Done when: You can ask "list my GitHub issues" and get real data.

---

Phase 2: Memory Architecture (Week 1-2, ~3 hours)

Goal: Agent remembers who you are, what you're building, and what matters.

Core memory files to create:

CODEBLOCK2

SOUL.md template:
CODEBLOCK3

MEMORY.md template:
CODEBLOCK4

Done when: You start a session and the agent knows your name, mission, and current priority without you explaining it.

---

Phase 3: Skill Architecture (Week 2, ~4 hours)

Goal: Agent has 5+ targeted capabilities installed as named skills.

Skill selection decision tree:
CODEBLOCK5

Skill quality checklist (for each skill you install):
CODEBLOCK6

Skill catalog file (create at project root):
CODEBLOCK7

Done when: You can say "use [skill]" and the agent knows exactly what framework to apply.

---

Phase 4: Agent Routing (Week 2-3, ~3 hours)

Goal: Right model for right task. Parallel when possible.

Model Routing Matrix:

Task Type	Use	Cost Level
File reads, status checks, simple lookups	Haiku / cheap model	$
Writing, content, standard analysis

Sonnet / mid model | $$ |
| Architecture decisions, complex strategy | Opus / best model | $$$ |
| Sub-agents doing simple tasks | Haiku | $ |
| Sub-agents doing writing | Sonnet | $$ |

Sub-agent trigger rules:
CODEBLOCK8

Done when: You're running parallel sub-agents on independent tasks and using Haiku for simple work automatically.

---

Phase 5: Output Integration (Week 3, ~3 hours)

Goal: Agent outputs land in the right place automatically.

Integration checklist:
CODEBLOCK9

Done when: You get a Slack notification from your agent without asking for it.

---

Architecture Reference Diagrams

Minimal Viable AI OS (Good)

CODEBLOCK10

Standard AI OS (Better)

CODEBLOCK11

Full AI OS (Best)

CODEBLOCK12

---

Common Anti-Patterns (and fixes)

Anti-Pattern	Symptom	Fix
Context amnesia	Re-explaining yourself every session	Build Layer 2 memory stack
One-size-fits-all model

Burning credits on simple tasks | Apply Model Routing Matrix |
| Serial agent work | Tasks take 10x longer than needed | Enable sub-agent parallelism |
| Prompt not skill | Same prompts repeated every session | Package into SKILL.md |
| No approval gate | Agent sends external messages unexpectedly | Add gate to all write ops |
| Config not backed up | One system wipe loses everything | Git-commit your config |

---

Example Session

User prompt:

"Audit my current AI setup and tell me what to build next."

Agent response using this skill:

1. 1. Asks user to self-score each layer of the OS Stack Scorecard
2. Calculates total score and identifies weakest layer
3. Generates prioritized build order based on scores
4. Provides specific implementation checklist for the weakest layer
5. Estimates time investment per phase
6. Books follow-up check: "In 1 week, re-score Layer [X]"

---

Bundle Note

This skill is part of the AI Setup & Productivity Pack ($79 bundle):

• - MCP Server Setup Kit ($19)
• Agentic Loop Designer ($29)
• AI OS Blueprint ($39) — you are here
• Context Budget Optimizer ($19)
• Non-Technical Agent Quickstart ($9)

Save $36 with the full bundle. Built by @RemyClaw.